39 lines
1.1 KiB
Python
39 lines
1.1 KiB
Python
|
import numpy as np
|
||
|
|
import matplotlib.pyplot as plt
|
||
|
|
from sklearn.mixture import GaussianMixture
|
||
|
|
|
||
|
|
def file_filter(file):
|
||
|
|
filter_data = []
|
||
|
|
fit_data = np.array([])
|
||
|
|
|
||
|
|
data = np.loadtxt(file, dtype=np.uint16)
|
||
|
|
|
||
|
|
model = GaussianMixture(n_components=2)
|
||
|
|
model.fit(data)
|
||
|
|
|
||
|
|
ny = model.predict(data)
|
||
|
|
for i in np.unique(ny):
|
||
|
|
idx = np.where(ny == i)[0]
|
||
|
|
fit_data = idx if len(idx) > len(fit_data) else fit_data
|
||
|
|
filter_data.append(data[idx])
|
||
|
|
|
||
|
|
return filter_data, data[fit_data]
|
||
|
|
|
||
|
|
def draw_filter(data, title):
|
||
|
|
fig = plt.figure(figsize=(8, 8))
|
||
|
|
ax = fig.add_subplot(1, 1, 1)
|
||
|
|
for cluster in data:
|
||
|
|
ax.scatter(cluster[:, 0], cluster[:, 1], s=0.1)
|
||
|
|
fig.savefig(title, facecolor='w', transparent=False)
|
||
|
|
plt.close()
|
||
|
|
|
||
|
|
def get_hist(data, delta=1, maxN=50):
|
||
|
|
step = delta
|
||
|
|
edge = np.arange(data.min(), data.max() + 1, step)
|
||
|
|
count, _ = np.histogram(data, bins=edge)
|
||
|
|
while count.max() <= maxN:
|
||
|
|
step += delta
|
||
|
|
edge = np.arange(data.min(), data.max() + 1, step)
|
||
|
|
count, _ = np.histogram(data, bins=edge)
|
||
|
|
return count, (edge[1:] + edge[:-1]) / 2
|